Machine learning for RNA-targeting drug design

TL;DR

This review discusses machine learning methods for RNA-targeting drug design, highlighting the challenges, current approaches, and the need for standardized evaluation to improve predictive models in this emerging field.

Contribution

It provides a comprehensive comparison of existing machine learning tools for RNA drug design and proposes standardized evaluation benchmarks.

Findings

Current models have limited ability to predict drug-RNA interactions.

RNA-specific machine learning approaches are emerging but need standardization.

Benchmark results highlight gaps in predictive accuracy.

Abstract

Targeting RNA with small molecules offers significant therapeutic potential. Machine learning could substantially accelerate preclinical drug discovery, from hit identification to lead optimization. Yet a fundamental limitation emerges: drug design machine learning models, tailored for proteins, are not readily applicable to RNAs because of fundamental differences between RNAs and proteins in both structural characteristics and interactions with small molecules. RNA-specific approaches have consequently emerged, primarily focusing on binding site identification and virtual screening. In this review, we comprehensively compare machine learning tools for RNA-targeting drug design according to the tasks they address, their methodology and their relevance in RNA-specific contexts. As open challenges will catalyze new method development, we emphasize the need for standardized, drug design-specific evaluation approaches. We provide clear guidelines to establish these standards along with a benchmark assessing the ability of current machine learning models to predict specific drug-RNA interactions.